scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-05 02:41:56 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 49

docs(prometheus): proxy-only config examples, remove SDK snippets

Browse source
This commit is contained in:
Ishaan Jaffer 2026-03-23 11:58:29 -07:00
parent b942a553ef
commit dfda838757
1 changed files with 2 additions and 35 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

37
docs/my-website/docs/proxy/metrics.md
View file

@ -4,22 +4,12 @@
By default, LiteLLM uses a fixed set of histogram buckets for all latency metrics. You can override them to match your SLOs.
**Proxy config (`litellm_settings`)**
```yaml
litellm_settings:
success_callback: ["prometheus"]
prometheus_latency_buckets: [0.05, 0.1, 0.25, 0.5, 1.0, 2.0, 5.0, .inf]
```
**Python SDK**
```python
import litellm
litellm.prometheus_latency_buckets = (0.05, 0.1, 0.25, 0.5, 1.0, 2.0, 5.0, float("inf"))
```
Applies to all histogram metrics:
- `litellm_request_total_latency_metric`
- `litellm_llm_api_latency_metric`
@ -34,8 +24,6 @@ Applies to all histogram metrics:
Disable specific metrics entirely — they are replaced by no-ops and never registered in Prometheus.
**Proxy config (`litellm_settings`)**
```yaml
litellm_settings:
success_callback: ["prometheus"]
@ -44,25 +32,12 @@ litellm_settings:
- litellm_request_queue_time_seconds
```
**Python SDK**
```python
import litellm
litellm.prometheus_exclude_metrics = [
"litellm_overhead_latency_metric",
"litellm_request_queue_time_seconds",
]
```
---
## Exclude Labels
Strip label dimensions from **all** metrics. Useful for reducing cardinality.
**Proxy config (`litellm_settings`)**
```yaml
litellm_settings:
success_callback: ["prometheus"]
@ -72,14 +47,6 @@ litellm_settings:
- client_ip
```
**Python SDK**
```python
import litellm
litellm.prometheus_exclude_labels = ["end_user", "user_agent", "client_ip"]
```
> `prometheus_exclude_labels` is applied after any `prometheus_metrics_config` include-label filtering.
---
@ -91,7 +58,7 @@ litellm.prometheus_exclude_labels = ["end_user", "user_agent", "client_ip"]
curl -X GET "http://0.0.0.0:4000/daily_metrics" -H "Authorization: Bearer sk-1234"
```
## Response format
## Response format
```json
[
daily_spend = [
@ -127,4 +94,4 @@ curl -X GET "http://0.0.0.0:4000/daily_metrics" -H "Authorization: Bearer sk-123
]
```
```